Genome-scale activation screen identifies a lncRNA locus regulating a gene neighbourhood

Abstract

Mammalian genomes contain thousands of loci that transcribe long noncoding RNAs (lncRNAs), some of which are known to carry out critical roles in diverse cellular processes through a variety of mechanisms. Although some lncRNA loci encode RNAs that act non-locally (in trans), there is emerging evidence that many lncRNA loci act locally (in cis) to regulate the expression of nearby genes-for example, through functions of the lncRNA promoter, transcription, or transcript itself. Despite their potentially important roles, it remains challenging to identify functional lncRNA loci and distinguish among these and other mechanisms. Here, to address these challenges, we developed a genome-scale CRISPR-Cas9 activation screen that targets more than 10,000 lncRNA transcriptional start sites to identify noncoding loci that influence a phenotype of interest. We found 11 lncRNA loci that, upon recruitment of an activator, mediate resistance to BRAF inhibitors in human melanoma cells. Most candidate loci appear to regulate nearby genes. Detailed analysis of one candidate, termed EMICERI, revealed that its transcriptional activation resulted in dosage-dependent activation of four neighbouring protein-coding genes, one of which confers the resistance phenotype. Our screening and characterization approach provides a CRISPR toolkit with which to systematically discover the functions of noncoding loci and elucidate their diverse roles in gene regulation and cellular function.

Extended Data Figure 1. Genome-scale activation screen for lncRNA loci involved in BRAF inhibitor resistance

a, Scatterplots showing lncRNA-targeting and non-targeting sgRNA frequencies after vemurafenib (vemu) or control treatment from n = 4 infection replicates. b, RIGER P values for the top 100 hits from the previous SAM protein-coding gene screen compared to the SAM lncRNA loci screen. c, For each candidate lncRNA locus, 10 sgRNAs were designed to target the proximal promoter region (800 bp upstream of the TSS). The relationship between the highest sgRNA enrichment in vemurafenib-treated compared to control condition across screening bioreps (n = 4) and respective spacer position suggests that sgRNAs targeting closer to the annotated TSS are not necessarily more effective, consistent with previous results .

Extended Data Figure 2. Validation of candidate lncRNA loci for vemurafenib resistance

Vemurafenib resistance for A375 transduced with SAM and individual sgRNAs targeting the top 16 candidate lncRNA loci normalized to a non-targeting (NT) sgRNA. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01.

Extended Data Figure 3. Activation of candidate lncRNA loci mediate vemurafenib resistance by potentially acting locally to regulate expression of nearby genes

a, Heat map showing expression of gene/signature markers for BRAF inhibitor sensitivity (top), expression of candidate lncRNA loci (middle), and RNA-seq signature of gene expression changes upon activation of candidate lncRNA loci (bottom) in 113 different BRAF (V600) patient melanoma samples (primary or metastatic) from The Cancer Genome Atlas. All associations are measured using the information coefficient (IC) between the index and each of the features and P values are determined using a permutation test. Panels show Z scores. b, Vemurafenib resistance of A375 cells overexpressing each candidate lncRNA cDNA or protein-coding gene normalized to GFP. GPR35 and LPAR1 are positive controls identified previously . The same set of sgRNAs targeted TCONS_00012395 and TCONS_00011252; NR_034078 and NR_034079; TCONS_00015940_1 and TCONS_00015940_2. c, Expression of NR_109890 and its neighboring gene EBF1 after SAM activation of NR_109890. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; *P < 0.05. ns = not significant.

Extended Data Figure 4. Topological domain in the EMICERI locus is consistent across cell types

Hi-C data and topological domain annotations (dotted lines) in the EMICERI locus from 7 cell lines . Heat map shows KR-normalized contact matrix at 5-kb resolution. Domain annotations for chromosome 9 were not available in K562, but the same topological domain structure is evident.

Extended Data Figure 5. Dosage-dependent upregulation of the EMICERI locus is specific to activation of EMICERI at its conserved regulatory element

a, TopHat alignment of RNA-seq paired-end reads suggests that EMICERI is located at chr9:27,529,917-27,531,782 and EMICERII at chr9:27,535,711-27,540,711 (UCSC hg19) (Supplementary Note 6). A375 ATAC-seq and phastCons conservation scores for primates, placental mammals, and vertebrates at the EMICERI locus. Scale bar, 1 kb. b, Expression of EMICERI and its neighboring genes MOB3B, IFNK, EQTN, and C9orf72 after transduction with sgRNAs targeting SAM to the promoters of neighboring genes. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01; *P < 0.05. ns = not significant. ND = not detected.

Extended Data Figure 6. Activation of EMICERI mediates vemurafenib resistance through MOB3B

a, Expression of the neighboring genes or EMICERI/II after cDNA overexpression compared to GFP control. b, cDNA overexpression of top hits from the SAM protein-coding gene screen for vemurafenib resistance (GPR35 and LPAR1) or MOB3B compared to GFP control. c, Vemurafenib dose response curves for A375 cells overexpressing cDNA or GFP control. d, Vemurafenib half maximal inhibitory concentration (IC50) for the same conditions in (c). e, ATARiS gene-level scores from the Achilles Project that reflect genetic vulnerabilities of A375. Lower ATARiS gene-level scores indicate stronger dependency on the gene. Rank of MOB3B, 1,084; IFNK, 3,078; EQTN, 15,939. f to h, Western blots of A375 stably overexpressing MOB3B cDNA or GFP control after vemurafenib or control (DMSO) treatment. i, Expression of EMICERI and MOB3B after SAM activation in different melanoma cell lines. All values are mean ± SEM with n = 4. ****P < 0.0001; **P < 0.01; *P < 0.05. ND = not detected.

Extended Data Figure 7. EMICERI expression is strongly correlated with MOB3B expression and vemurafenib sensitivity in melanoma cell lines and patient samples

a, Heat map showing expression of genes in the EMICERI locus in 113 different BRAF (V600) patient melanoma samples (primary or metastatic) from The Cancer Genome Atlas. Samples are sorted by EMICERI expression. b, Heat map showing expression of genes in the EMICERI locus in melanoma cell lines from the Cancer Cell Line Encyclopedia (CCLE) sorted by EMICERI expression. c, Heat map showing sensitivity to different drugs (top), expression of genes in the EMICERI locus (middle), and MOB3B cDNA overexpression RNA-seq signature (bottom; see Methods for signature generation) in melanoma cell lines from CCLE. Drug sensitivities are measured as Activity Areas. The melanoma cell lines are sorted by PLX-4720 (vemurafenib) drug sensitivity. RAF inhibitors: PLX-4720 and RAF265; MEK inhibitors: AZD6244 and PD-0325901. d, Expression of EMICERI and MOB3B in two primary patient-derived BRAF(V600E) melanoma cell lines. e, Vemurafenib dose response curves for the same cell lines. f, Vemurafenib half maximal inhibitory concentration (IC50) for the same conditions as (e). All associations are measured using the information coefficient (IC) between the index and each of the features and P values are determined using a permutation test. Heat maps show Z scores. All values are mean ± SEM with n = 4. ****P < 0.0001; *P < 0.05.

Extended Data Figure 8. Transcriptional activation of EMICERI modulates expression of neighboring genes

a, Gel confirming polyadenylation signal (pAS) insertion into all 3 copies of EMICERI for each pAS clone. b to c, Basal expression of EMICERI and MOB3B for the wild type and pAS clones. d to f, Expression of C9orf72, IFNK, and EQTN after targeting SAM to EMICERI for the wild type and pAS clones. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; *P < 0.05. ns = not significant.

Extended Data Figure 9. Transcriptional activation of EMICERI confers vemurafenib resistance

a, Vemurafenib dose response curves for wild type and polyadenylation signal (pAS) clones transduced with SAM and EMICERI-targeting or non-targeting (NT) sgRNAs. b, Vemurafenib half maximal inhibitory concentration (IC50) for the same conditions as (a). All values are mean ± SEM with n = 4. *P < 0.05. ns = not significant.

Extended Data Figure 10. EMICERI and MOB3B act reciprocally to regulate each other through the process of transcription

a, Expression of EMICERI and MOB3B after antisense oligonucleotide (ASO) knockdown of EMICERI in the context of SAM activation. b, Expression of MOB3B and neighboring genes in A375 cells transduced with non-targeting (NT) or MOB3B-targeting sgRNAs and dCas9. c, Expression of MOB3B and EMICERI after ASO knockdown of MOB3B in the context of SAM activation. c, All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01; *P < 0.05. ns = not significant.

Figure 1. Genome-scale activation screen identifies lncRNA loci involved in vemurafenib resistance

a, A375 cells expressing SAM effectors are transduced with the pooled sgRNA library targeting >10,000 lncRNA TSSs and treated with BRAF inhibitor vemurafenib or DMSO (control) for 14 days. Deep sequencing identified changes in sgRNA distribution. b, Box plot showing the distribution of sgRNA frequencies after vemurafenib or control treatment from n = 4 infection replicates. c, Scatterplot showing enrichment of sgRNAs targeting 6 candidate lncRNA loci. d, RIGER P values of the candidate lncRNA loci. e, Validation of vemurafenib resistance and transcriptional activation in A375 cells expressing individual sgRNAs targeting 6 candidate lncRNA loci or non-targeting (NT) control sgRNA. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01; *P < 0.05.

Figure 2. Activation of the EMICERI promoter produces dosage-dependent upregulation of neighboring genes

a, Genomic locus of EMICERI contains four neighboring genes (EQTN, MOB3B, IFNK, and C9orf72) and a putative enhancer. b, Expression of EMICERI and its neighboring genes after transduction with non-targeting (NT) or EMICERI-targeting sgRNAs and SAM. ND = not detected. c, Expression of EMICERI and MOB3B after transduction with sgRNAs tiling SAM across the EMICERI locus normalized to a NT sgRNA. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01.

Figure 3. MOB3B mediates vemurafenib resistance through the Hippo signaling pathway in melanoma models

a, Vemurafenib resistance of A375 cells overexpressing each neighboring gene or lncRNA cDNA normalized to GFP. b, Western blots of LATS1, YAP, and TAZ in A375 stably overexpressing MOB3B cDNA or GFP after vemurafenib or control (DMSO) treatment. c, Schematic of MOB3B mechanism in the Hippo signaling pathway. d, Vemurafenib dose response curves for EMICERI activation in different melanoma cell lines. e, Vemurafenib half maximal inhibitory concentration (IC50) for the same conditions in (d). f, Heat map showing expression of gene/signature markers for BRAF inhibitor sensitivity (top), expression of genes in the EMICERI locus (middle), and MOB3B overexpression RNA-seq signature scores (bottom) in 113 different BRAF (V600) patient melanoma samples (primary or metastatic) from The Cancer Genome Atlas. All associations are measured using the information coefficient (IC) between the index and each of the features and P values are determined using a permutation test. Panels show Z scores. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01. *P < 0.05. ns = not significant.

Figure 4. Transcription of EMICERI modulates MOB3B expression

a, Targeting positions of sgRNAs and antisense oligonucleotides (ASOs) in the EMICERI and MOB3B locus. b, Expression of EMICERI and its neighboring genes in A375 cells transduced with non-targeting (NT) or EMICERI-targeting sgRNAs and dCas9. c, Schematic for bimodal perturbation of EMICERI transcription. sgRNAs 1-3 use MS2 loops to recruit MS2-P65-HSF1 to dCas9 to activate EMICERI, whereas sgRNAs 4-5 recruit only dCas9 to repress EMICERI. d, Correlation between MOB3B and EMICERI expression produced by different combinations of sgRNAs with and without MS2 loops. e, Schematic for inserting polyadenylation signals (pAS) downstream of the EMICERI TSS. SV40, Simian virus 40; PGK, phosphoglycerate kinase. f, EMICERI expression after SAM activation of EMICERI for the wild type and pAS clones. g, MOB3B expression after the same perturbations as (f). h, Vemurafenib resistance after SAM activation of EMICERI. i, Expression of EMICERI and MOB3B after ASO knockdown of EMICERI in the context of SAM activation. j, Expression of MOB3B and EMICERI after ASO knockdown of MOB3B in the context of SAM activation. All values are mean ± SEM with n = 4. ****P < 0.0001; ***P < 0.001; **P < 0.01; *P < 0.05. ns = not significant.